Research map / Vision-language and multimodal / Visual question answering
TallyQA: Answering Complex Counting Questions
Manoj Acharya, Kushal Kafle, Christopher Kanan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add object-background relationships (ablation) | RCN · TallyQA Test-Simple | accuracy (%): 69.4 -> 71.8 | Improved |
| add object-background relationships (ablation) | RCN · TallyQA Test-Simple | RMSE: 1.18 -> 1.13 | Improved |
| add object-background relationships (ablation) | RCN · TallyQA Test-Complex | accuracy (%): 51.8 -> 56.2 | Improved |
| add object-background relationships (ablation) | RCN · TallyQA Test-Complex | RMSE: 1.50 -> 1.43 | Improved |
| remove proposal location features (ablation) | RCN · HowMany-QA | accuracy (%): 5.4% decrease in accuracy (absolute) | Hurt |
| remove proposal location features (ablation) | RCN · TallyQA Test-Simple | accuracy (%): 2.8% decrease in accuracy (absolute) | Hurt |
| remove proposal location features (ablation) | RCN · TallyQA Test-Complex | accuracy (%): 2.4% decrease in accuracy (absolute) | Hurt |
| use RCN rather than Zhang et al. | counting models · TallyQA positional reasoning questions | accuracy (%): 6.38% absolute | Improved |
| apply simple non-maximal suppression to prune overlapping boxes (ablation) | RCN · open-ended counting | performance | No clear effect |
Closest papers by meaning
- Interpretable Counting for Visual Question Answering (ICLR 2018 · similarity 0.91)
- Learning to Count Objects in Natural Images for Visual Question Answering (ICLR 2018 · similarity 0.89)
- KVQA: Knowledge-Aware Visual Question Answering (AAAI 2019 · similarity 0.88)
- OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge (CVPR 2019 · similarity 0.88)
- When Open-Vocabulary Visual Question Answering Meets Causal Adapter: Benchmark and Approach (AAAI 2025 · similarity 0.86)
- CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
